CN116611417B - Automatic article generating method, system, computer equipment and storage medium - Google Patents
Automatic article generating method, system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116611417B CN116611417B CN202310615917.1A CN202310615917A CN116611417B CN 116611417 B CN116611417 B CN 116611417B CN 202310615917 A CN202310615917 A CN 202310615917A CN 116611417 B CN116611417 B CN 116611417B
- Authority
- CN
- China
- Prior art keywords
- article
- text
- paragraph
- paragraphs
- generation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000000605 extraction Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 5
- 230000014509 gene expression Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 2
- 239000000047 product Substances 0.000 description 26
- 238000003058 natural language processing Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000010865 sewage Substances 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000013518 transcription Methods 0.000 description 1
- 230000035897 transcription Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical field of automatic article generation, in particular to an automatic article generation method, an automatic article generation system, computer equipment and a storage medium, which comprise S1, initializing article generation template library data; s2, inputting a primary keyword, and selecting a template from the article generation template library; s3, selecting paragraphs to be generated according to the selected templates, and searching the web page in real time to obtain web page contents; s4, extracting a required content main body according to the acquired webpage content to generate a text; s5, splitting the text paragraphs according to the generated text, randomly selecting split paragraph combinations to generate articles, and ending paragraph generation; s6, re-executing the steps S3-S5, and generating the next paragraph until the generation of all paragraphs is completed. The method and the device have the effects of automatically generating the articles with rich and various contents according to the related keywords, reducing the labor cost and the time cost and improving the quality of the articles.
Description
Technical Field
The present application relates to the field of automatic article generation technology, and in particular, to an automatic article generation method, system, computer device, and storage medium.
Background
Artificial Intelligence (AI) is a new technical science that studies, develops theories, methods, techniques and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the nature of intelligence and to produce a new intelligent machine that can react in a similar manner to human intelligence, research in this field including robotics, speech recognition, image recognition, natural language processing, and expert systems.
The field of article generation also gradually tends to be artificial intelligence, and the method for article generation comprises automatic article generation through multimedia transcription and manual article editing. The method has the advantages that the data sources are single, so that the generated articles are not rich in content and extensive in themes, the process of manually editing the multimedia articles is complex, time and complexity are high, and unnecessary expenditure of manpower and financial resources is caused. In the prior art, in the field of automatic article generation, articles are generated according to keywords, but for articles such as journals, documents and news, the articles are usually manually written, but in the manual writing mode, a large amount of time is consumed to complete the writing work of a limited number of articles, and the written article quality is closely related to the experience level of personnel, so that the article quality is not easy to control.
Disclosure of Invention
In order to automatically generate various articles with rich contents according to related keywords, the labor cost and the time cost are reduced, and the article quality is improved, the application provides an automatic article generation method, an automatic article generation system, computer equipment and a storage medium.
In a first aspect, the present application provides an automatic article generating method, which adopts the following technical scheme: an automatic article generation method, comprising:
s1, initializing article generation template library data;
s2, inputting a primary keyword, and selecting a template from the article generation template library;
s3, selecting paragraphs to be generated according to the selected templates, and searching the web page in real time to obtain web page contents;
s4, extracting a required content main body according to the acquired webpage content to generate a text;
s5, splitting the text paragraphs according to the generated text, randomly selecting split paragraph combinations to generate articles, and ending paragraph generation;
s6, re-executing the steps S3-S5, and generating the next paragraph until the generation of all paragraphs is completed.
By adopting the technical scheme, the template is generated through various pre-established articles, the template library is enriched, so that a user has more choices, the user can select a proper template according to actual needs and combine main keywords, operations of real-time web search, article main body content extraction, paragraph splitting and random combination generation are performed according to the choices of the user, the articles are finally generated, the whole-network real-time web search can not limit the paths of article acquisition, the generated text content is not limited by the templates, the real-time search can always cover the latest content of the acquired text content, and therefore the articles with rich and various contents are generated.
Preferably, the selecting the paragraphs to be generated according to the selected template, and performing real-time web search to obtain web content further includes the following steps:
and determining auxiliary keywords according to the selected paragraphs, and combining the main keywords and the auxiliary keywords to perform real-time web page searching.
Through adopting above-mentioned technical scheme, combination primary keyword and auxiliary keyword, can be when carrying out real-time web search, more accurate search the required article content of user for obtain the content of article abundanter, various, make the content source wider, do not restrict the content of auxiliary keyword, thereby make the article that generates have wider content coverage.
Preferably, the extracting the required content body according to the acquired webpage content, and generating the text further comprises the following steps:
defining a function for extracting paragraph main body content, defining the searched webpage as a label, and searching sub-nodes under the label by utilizing the function;
traversing each child node, judging whether the child node is paragraph main body content required by a user, and if so, extracting all text content under the child node; if not, the text content under the child node is directly removed.
By adopting the technical scheme, the searched web page content is extracted to remove useless information except the main text in the web page, so that the generated articles are ensured not to be disordered.
Preferably, the step of splitting the text paragraph according to the generated text, and randomly selecting the split paragraph combination to generate the article, wherein the paragraph generation end further comprises the following steps:
and replacing daily expressions according to the generated articles to form new article texts.
By adopting the technical scheme, the generated article is replaced by sentences, so that the generated article and the existing article cannot be repeated at great space, the semantic can be adjusted in the replacing process, and the article quality is improved.
In a second aspect, the present application provides an automatic article generating system, which adopts the following technical scheme:
an automatic article generation system comprising:
the control module is used for controlling the input and the output of the article automatic generation system;
the input selection module is connected with the control module and is used for receiving a control signal of the control module, inputting keywords, and selecting templates and paragraphs according to the input keywords;
the template library module is connected with the control module and is used for receiving a control signal of the control module, establishing and storing paragraph structures and core directions of the templates generated by the articles of each category, providing the paragraph structures and core directions for a user to select, and transmitting the templates selected by the user to the control module;
and the article generating module is connected with the control module and is used for generating articles according to the templates transmitted by the control module.
By adopting the technical scheme, the automatic article generation work is realized through the cooperation of the control module, the input selection module, the template library module and the article generation module, the templates of various categories are established in the template library module for the user to select, the user inputs keywords, selects the templates and selects paragraphs through the input selection module, and the control module controls the article generation module to combine the templates selected by the user to perform the article generation work.
Preferably, the input selection module includes:
the keyword input unit is used for inputting the main keywords by a user and modifying or replacing the auxiliary keywords;
the template selection unit is connected with the keyword input unit and is used for selecting an article generating template according to keywords input by a user;
and the paragraph selection unit is connected with the template selection unit and is used for selecting paragraphs required to be generated according to the article generation template.
By adopting the technical scheme, the key word input unit is used for inputting the main key word and the auxiliary key word is used for modifying or replacing the auxiliary key word, the template selecting unit is used for selecting the templates of the article to be generated after the main key word and the auxiliary key word are determined, and the paragraph selecting unit is used for selecting the paragraphs to be generated by combining the selected templates after the templates are determined because the paragraph structures of each template are different.
Preferably, the article generating module includes:
the searching unit is used for carrying out full-network searching according to the template received by the article generating module and acquiring real-time webpage content;
the extraction and generation unit is connected with the search unit and is used for extracting text bodies in the webpage content and combining the text bodies to generate articles;
and the transmission unit is connected with the extraction and generation unit and is used for transmitting the article text generated by the extraction and generation unit to the control module.
By adopting the technical scheme, the search unit can search the web page by combining the determined primary keywords and the auxiliary keywords, the extraction generating unit extracts and combines the article main body according to the searched web page content, so that useless information and characters are removed, the generated article cannot be messy, and the transmission unit transmits the generated article to the control module.
Preferably, the extraction generating unit includes:
a splitting and combining subunit, configured to split paragraphs of the article generated by the extraction and generation unit, and randomly combine the split paragraphs to generate the article;
and the replacing subunit is connected with the splitting and combining subunit and is used for carrying out sentence replacement on the article generated by the splitting and combining subunit to generate a new article text.
By adopting the technical scheme, the article generated by the extraction and generation unit is an unsegmented paragraph, so that the generated article is split by splitting and combining the sub-units, the paragraph combination is randomly selected to generate the article, and the replacement sub-unit can replace the generated article to ensure that the generated article has no statement errors and is in a proper order, thereby improving the quality of the generated article.
In a third aspect, the present application provides a computer device comprising one or more processors and a memory, the memory having stored thereon a computer program to be loaded by the processor and to perform the above method.
In a fourth aspect, the present application provides a computer readable storage medium storing a computer program capable of being loaded by a processor and executing the above method.
Compared with the related art, the embodiment of the application provides an automatic article generating method, an automatic article generating system, a computer device and a storage medium, wherein the main keywords and the auxiliary keywords are combined to perform real-time webpage retrieval, and the searched webpage contents are subjected to article main body content extraction, splitting and random combination, so that various articles with rich contents are generated, the contents for generating the articles are richer and more various, the content sources are wider, the generated articles have wider content coverage, the automatic article generating method does not limit the webpage searching range, the timeliness is higher, the labor cost and the time cost are reduced, the condition that the quality of the articles is different due to different experience of different writers is avoided, and the quality of the articles is improved to a certain extent.
Drawings
FIG. 1 is a flow chart of an automatic article generating method according to an embodiment of the present application;
FIG. 2 is a block flow diagram of step S2 and step S3 in the method for automatically generating articles according to the embodiment of the present application;
FIG. 3 is a block flow diagram of step S5 in the method for automatically generating articles according to the embodiment of the present application;
FIG. 4 is a block diagram of an article auto-generation system according to an embodiment of the present application.
Reference numerals illustrate: 1. a control module; 2. an input selection module; 21. a keyword input unit; 22. a template selection unit; 23. a paragraph selection unit; 3. a template library module; 4. an article generation module; 41. a search unit; 42. an extraction generation unit; 421. splitting the combined subunits; 422. replacing the subunit; 43. and a transmission unit.
Detailed Description
The present application will be described in further detail with reference to fig. 1 to 4.
While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, 2 and 3, the automatic article generating method disclosed by the application comprises the following steps:
s1, initializing article generation template library data.
Specifically, template data in an article generating template library is loaded, wherein the article generating template library comprises paragraph structures and core directions of various types of articles, and the paragraph structures and the core directions determine a basic framework of the articles.
The core directions include enterprise report, product news, local news, industry and market dynamics, exhibition activities, etc., each core direction is composed of predefined paragraphs, for example, product news, and the paragraph structure can be divided into: the first section is the introduction of a product, the fixed term is that "A is a B-class product, D is realized by using C, the product is one of products of E company camping, and the product has certain advantages in F industry"; the second section is introduced for the enterprise background to which the product belongs, and comprises basic information such as establishment time of the enterprise, the industry to which the product belongs, a main business and the like; the third section is product parameters, product characteristics, working principles, technical indexes and the like, and the fixed term is 'known from F, the product …'; the fourth section is after-sale guarantee service of the product, and can comprise the steps of product operation flow, maintenance, fault solution and the like; the fifth section is the existing customer case, i.e., which customers are currently using the product; the sixth section is product comparison, and is compared with products of different models of G company, and the product comparison comprises introduction and characteristics of each product; the seventh section is the application/advantage of the product in industry and the market analysis/prospect of the supply and demand end.
The specific content of the article generating template and related industries, products and enterprises are required to be determined according to the primary keywords and the auxiliary keywords, and also taking product news as an example, A is a B-type product, wherein A is a product word, namely the primary keywords, the primary content of the product news is unfolded around the primary keywords A, B is the industry, namely the auxiliary keywords and is used as derivative content of the article, and in order to enrich the paragraph content, the auxiliary keywords are preset corresponding to the specific content of each paragraph, for example, the auxiliary keywords in the seventh paragraph can be preset as development, foreground and the like.
It should be noted that, the core direction and paragraph structure are not limited, and only one case of the product news is taken as an example for illustration in the embodiment of the present application.
S2, inputting a primary keyword, and selecting a template from the article generation template library.
Specifically, the user inputs the primary key words, and selects the corresponding templates of the articles to be generated in the article generation template library, for example, the user needs to generate one or more articles for industry analysis in the sewage treatment field, the user inputs the primary key words for sewage treatment, and the next operation can be performed by selecting the article templates for industry analysis.
The user can modify the paragraph composition of the template according to the actual requirement, namely, the paragraph composition of each core direction can be adjusted at any time according to the actual condition, thereby modifying the paragraph names and auxiliary keywords and deleting unnecessary paragraphs.
The step S2 further includes:
s21, generating an article according to the selected template one-key.
Specifically, if the user does not need to adjust the paragraphs or adjust the auxiliary keywords of each paragraph, one or more articles can be generated by directly selecting one key according to the preset template paragraph composition and the preset auxiliary keywords, for example, the user inputs a main keyword for sewage treatment, and the articles required by the user can be generated by clicking one key after selecting the article template analyzed by the industry, so that more choices are provided for the user to adapt to the requirements of different users.
It should be noted that the process of generating an article by one key is the same as the process of generating a paragraph, and the following steps may be specifically referred to.
S3, selecting paragraphs to be generated according to the selected templates, and searching the web page in real time to obtain web page contents.
Specifically, the user continues to select a paragraph to be generated according to the selected template, and selects a paragraph to be generated according to the paragraph selection word, for example, also taking industry analysis as an example, the paragraph structure of the preset industry analysis template is as follows: the first section is industry development; the second section is the technical feature of the industry; the third section is a process adopted in the industry; the fourth section is the environmental background of the industry. The development, technical characteristics and process and environmental background are adopted as paragraph selection words displayed to the user, and the user can autonomously determine the needed paragraphs through the paragraph selection words to search the webpage in real time, so that the searched webpage content is obtained.
It should be noted that, since the web page information is updated continuously, the real-time web page search does not limit the way of text acquisition, and ensures that the acquired web page text content always covers the latest content.
The step S3 further includes:
s31, determining auxiliary keywords according to the selected paragraphs, and combining the main keywords and the auxiliary keywords to perform real-time web page searching.
Specifically, in order to ensure the accuracy and richness of the content of each paragraph of the generated article, the user can supplement or modify the auxiliary keywords according to the content of the selected paragraph, the content of the auxiliary keywords is not limited, the randomness of web page searching is reflected, so that more comprehensive content searching is conveniently performed in the web page, and the user can acquire the web page content with wider coverage and latest.
S4, extracting the required paragraph main body content according to the acquired webpage content, and generating a text.
Since the web page content searched according to the main keywords and the auxiliary keywords may contain irrelevant contents such as titles, links, advertisements, pictures and the like in addition to the main content of the paragraph required by the user, the contents other than the main content of the paragraph need to be removed.
The step S4 further includes:
s41, defining a function for extracting main body content of the paragraph, defining the searched webpage as a label, and searching sub-nodes under the label by utilizing the function.
Specifically, in order to extract the paragraph main body content required by the user, the subsequent calling work is also facilitated, a find function for extracting the paragraph main body content is defined, wherein the searched web page is defined as a body label, the body label is called, each sub-node under the body label is searched, and the sub-nodes include but are not limited to titles, links, articles and the like.
S42, traversing each child node, judging whether the child node is paragraph main body content required by a user, and if so, extracting all text content under the child node; if not, the text content under the child node is directly removed.
Specifically, the method includes the steps that a weight value is preset to be the length of extracted text, when the text length under a child node is obtained, the webpage content under a body label is subjected to reduction processing, namely irrelevant contents (titles, links and articles) in the searched webpage content are removed, the reduction processing is carried out according to a rule that the weight value is higher when the weight value is closer to the center of the main body of the paragraph, the weight value is lower when the weight value is farther from the center of the main body of the paragraph, the child node with the highest weight value is recorded through referencing weight value parameters of each child node, the density center is screened out, direct text is firstly extracted, namely the text content of a complete paragraph under the child node is firstly extracted, then the reduction processing is repeated, indirect text is extracted, namely the text content of the scattered paragraphs is extracted, and the direct text and the indirect text are combined to generate the required main body content of the paragraph.
Further, the operation of removing the empty characters before and after the paragraph is carried out on the extracted direct text and indirect text, and the extracted direct text and indirect text are combined into a character string, so that a complete text which is not segmented is obtained.
S5, splitting text paragraphs according to the generated text, randomly selecting split paragraph combinations to generate articles, and ending paragraph generation.
Specifically, in order to ensure randomness of article generation, the unsegmented text with the blank characters removed is split, namely the unsegmented text is cut into a plurality of natural segments according to natural segments, the cut natural segments are randomly selected according to the core direction of a template selected by a user, and then the randomly selected natural segments are combined to generate a new article.
The step S5 further includes:
s51, replacing daily expressions according to the generated articles to form new article texts.
Specifically, in order to reduce the repeatability of the generated text and the existing web page text, the sentences in the generated text are ensured to be correct and smooth, the quality of the generated text is improved, the generated text is analyzed and processed through an NLP (natural language processing) technology, the content of the text is understood, daily expressions in the text are replaced, and the language order is reorganized to form a new text.
The text of the generated article is processed by using NLP (natural language processing) technology, and the original meaning of the generated article is not affected or changed.
S6, re-executing the steps S3-S5, and generating the next paragraph until the generation of all paragraphs is completed.
Specifically, after the generation of the article text of one paragraph is finished, the user may generate the rest paragraphs in the template in the selected core direction according to the actual situation, so as to form one or several complete articles, that is, repeatedly execute steps S3-S5 until the generation of the article text of all paragraphs is finished, which is not repeated herein.
Based on the above method, the embodiment of the application also discloses an automatic article generating system, referring to fig. 4, the system comprises the following modules:
the control module 1 is used for controlling the input and the output of the article automatic generation system;
the input selection module 2 is connected with the control module 1 and is used for receiving a control signal of the control module 1, inputting keywords and selecting templates and paragraphs according to the input keywords;
further, the input selection module 2 further includes a keyword input unit 21, a template selection unit 22, and a paragraph selection unit 23.
A keyword input unit 21 for a user to input keywords;
a template selection unit 22 connected to the keyword input unit 21 for selecting an article generation template according to the keyword input by the user;
and a paragraph selection unit 23 connected to the template selection unit 22 for selecting a paragraph to be generated according to the selected article generation template.
The template library module 3 is connected with the control module 1, and is used for receiving the control signal of the control module 1, establishing and storing paragraph structures and core directions of the templates generated by the articles of each category, providing the paragraph structures and core directions for a user for selection, and transmitting the templates selected by the user to the control module 1;
and the article generating module 4 is connected with the control module 1 and is used for generating articles according to the templates transmitted by the control module 1.
Further, the article generating module 4 further includes a searching unit 41, an extraction generating unit 42, and a transmitting unit 43.
The searching unit 41 is configured to perform a full-network search according to the template received by the article generating module 4 and obtain real-time web content;
an extraction generation unit 42 connected to the search unit 41 for extracting text bodies in the web page contents and combining them to generate articles.
Further, the extraction generating unit 42 further includes a split combination subunit 421 and a replacement subunit 422.
A splitting and combining subunit 421, configured to split paragraphs of the article generated by the extraction generating unit 42, and randomly combine the split paragraphs to generate the article;
and the replacing subunit 422 is connected to the splitting and combining subunit 421, and is configured to perform sentence replacement on the article generated by the splitting and combining subunit 421, so as to generate a new article text.
And a transmission unit 43 connected to the extraction generating unit 42 for transmitting the text of the article generated by the extraction generating unit 42 to the control module 1.
The embodiment of the application also discloses computer equipment.
Specifically, the electronic device includes one or more processors and a memory, where the memory stores a computer program capable of being loaded and executed by the processor, and when the one or more computer programs are executed by the one or more processors, the one or more processors are caused to implement the steps of the method for automatically generating articles described above.
The embodiment of the application also discloses a computer readable storage medium.
Specifically, the computer-readable storage medium storing a computer program capable of being loaded by a processor and executing an article automatic generation method as one described above, for example, includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in the present application is not limited to the specific combinations of technical features described above, but also covers other technical features which may be formed by any combination of the technical features described above or their equivalents without departing from the spirit of the disclosure. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
Claims (9)
1. An automatic article generating method, comprising:
s1, initializing article generation template library data;
s2, inputting a primary keyword, and selecting a template from the article generation template library;
s3, selecting paragraphs to be generated according to the selected templates, and searching the web page in real time to obtain web page contents;
s4, extracting a required content main body according to the acquired webpage content to generate a text, wherein the method specifically comprises the following steps:
defining a function for extracting paragraph main body content, defining the searched webpage as a label, and searching sub-nodes under the label by utilizing the function;
traversing each child node, judging whether the child node is paragraph main body content required by a user, and if so, extracting all text content under the child node; if not, directly removing the text content under the child node;
s5, splitting the text paragraphs according to the generated text, randomly selecting split paragraph combinations to generate articles, and ending paragraph generation;
s6, re-executing the steps S3-S5, and generating the next paragraph until the generation of all paragraphs is completed.
2. The automatic article generating method according to claim 1, wherein the selecting paragraphs to be generated according to the selected templates and performing real-time web search to obtain web content further comprises the steps of:
and determining auxiliary keywords according to the selected paragraphs, and combining the main keywords and the auxiliary keywords to perform real-time web page searching.
3. The automatic article generating method according to claim 1, wherein the step of splitting the text paragraphs according to the generated text, randomly selecting split paragraph combinations to generate articles, and ending the paragraph generation further comprises the steps of:
and replacing daily expressions according to the generated articles to form new article texts.
4. An automatic article generating system, configured to implement the automatic article generating method of any one of claims 1 to 3, comprising:
the control module (1) is used for controlling the input and the output of the article automatic generation system;
the input selection module (2) is connected with the control module (1) and is used for receiving a control signal of the control module (1), inputting keywords, and selecting templates and paragraphs according to the input keywords;
the template library module (3) is connected with the control module (1) and is used for receiving a control signal of the control module (1), establishing and storing paragraph structures and core directions of the templates generated by the articles of each category, providing the paragraph structures and core directions for a user to select, and transmitting the templates selected by the user to the control module (1);
and the article generating module (4) is connected with the control module (1) and is used for generating articles according to the templates transmitted by the control module (1).
5. The automatic article generating system according to claim 4, wherein the input selection module (2) includes:
a keyword input unit (21) for a user to input a primary keyword and to modify or replace an auxiliary keyword;
the template selection unit (22) is connected with the keyword input unit (21) and is used for selecting an article generating template according to keywords input by a user;
and the paragraph selection unit (23) is connected with the template selection unit (22) and is used for selecting the paragraphs required to be generated according to the selected article generation template.
6. The automatic article generating system according to claim 5, wherein the article generating module (4) includes:
the searching unit (41) is used for carrying out full-network searching and acquiring real-time webpage content according to the template received by the article generating module (4);
an extraction generation unit (42) connected with the search unit (41) and used for extracting text bodies in the webpage content and combining the text bodies to generate articles;
and the transmission unit (43) is connected with the extraction generating unit (42) and is used for transmitting the article text generated by the extraction generating unit (42) to the control module (1).
7. The automatic article generating system according to claim 6, wherein the extraction generating unit (42) includes:
a splitting and combining subunit (421) configured to split paragraphs of the article generated by the extraction and generation unit (42), and randomly combine the split paragraphs to generate the article;
and the replacing subunit (422) is connected with the splitting and combining subunit (421) and is used for carrying out sentence replacement on the article generated by the splitting and combining subunit (421) to generate a new article text.
8. A computer device comprising one or more processors and a memory, the memory having stored thereon a computer program to be loaded by the processor and to perform the method according to any of claims 1-3.
9. A computer readable storage medium, storing a computer program capable of being loaded by a processor and executing the method according to any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310615917.1A CN116611417B (en) | 2023-05-26 | 2023-05-26 | Automatic article generating method, system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310615917.1A CN116611417B (en) | 2023-05-26 | 2023-05-26 | Automatic article generating method, system, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116611417A CN116611417A (en) | 2023-08-18 |
| CN116611417B true CN116611417B (en) | 2023-11-21 |
Family
ID=87677925
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310615917.1A Active CN116611417B (en) | 2023-05-26 | 2023-05-26 | Automatic article generating method, system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116611417B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402627A (en) * | 2011-12-31 | 2012-04-04 | 凤凰在线(北京)信息技术有限公司 | System and method for real-time intelligent capturing of article |
| CN106610927A (en) * | 2016-12-19 | 2017-05-03 | 厦门二五八网络科技集团股份有限公司 | Translation template-based internet article establishment method and system |
| CN106874248A (en) * | 2017-01-22 | 2017-06-20 | 百度在线网络技术（北京）有限公司 | article generation method and device based on artificial intelligence |
| CN108563620A (en) * | 2018-04-13 | 2018-09-21 | 上海财梵泰传媒科技有限公司 | The automatic writing method of text and system |
| CN109582945A (en) * | 2018-12-17 | 2019-04-05 | 北京百度网讯科技有限公司 | Article generation method, device and storage medium |
| CN109657223A (en) * | 2018-12-18 | 2019-04-19 | 安徽省泰岳祥升软件有限公司 | A kind of automatic writing method of official document and device |
| CN110264315A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Recommended information generation method and device |
| CN111046645A (en) * | 2019-12-11 | 2020-04-21 | 浙江大搜车软件技术有限公司 | Method and device for generating article, computer equipment and storage medium |
| CN111680482A (en) * | 2020-05-07 | 2020-09-18 | 车智互联（北京）科技有限公司 | Title image-text generation method and computing device |
| CN111859950A (en) * | 2020-06-18 | 2020-10-30 | 达而观信息科技（上海）有限公司 | Method for automatically generating lecture notes |
| CN111930929A (en) * | 2020-07-09 | 2020-11-13 | 车智互联（北京）科技有限公司 | Article title generation method and device and computing equipment |
| CN113609263A (en) * | 2021-09-30 | 2021-11-05 | 网娱互动科技(北京)股份有限公司 | Method and system for automatically generating articles |
| KR102410260B1 (en) * | 2022-03-07 | 2022-06-22 | 와이에스에이 주식회사 | Method, device and system for automatic creation and confirmation of advertisement content based on artificial intelligence |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3295328A4 (en) * | 2015-05-11 | 2019-01-16 | Ledohowski, Lindy | Methods and systems relating to context-specific writing frameworks |
-
2023
- 2023-05-26 CN CN202310615917.1A patent/CN116611417B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402627A (en) * | 2011-12-31 | 2012-04-04 | 凤凰在线(北京)信息技术有限公司 | System and method for real-time intelligent capturing of article |
| CN106610927A (en) * | 2016-12-19 | 2017-05-03 | 厦门二五八网络科技集团股份有限公司 | Translation template-based internet article establishment method and system |
| CN106874248A (en) * | 2017-01-22 | 2017-06-20 | 百度在线网络技术（北京）有限公司 | article generation method and device based on artificial intelligence |
| CN108563620A (en) * | 2018-04-13 | 2018-09-21 | 上海财梵泰传媒科技有限公司 | The automatic writing method of text and system |
| CN109582945A (en) * | 2018-12-17 | 2019-04-05 | 北京百度网讯科技有限公司 | Article generation method, device and storage medium |
| CN109657223A (en) * | 2018-12-18 | 2019-04-19 | 安徽省泰岳祥升软件有限公司 | A kind of automatic writing method of official document and device |
| CN110264315A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Recommended information generation method and device |
| CN111046645A (en) * | 2019-12-11 | 2020-04-21 | 浙江大搜车软件技术有限公司 | Method and device for generating article, computer equipment and storage medium |
| CN111680482A (en) * | 2020-05-07 | 2020-09-18 | 车智互联（北京）科技有限公司 | Title image-text generation method and computing device |
| CN111859950A (en) * | 2020-06-18 | 2020-10-30 | 达而观信息科技（上海）有限公司 | Method for automatically generating lecture notes |
| CN111930929A (en) * | 2020-07-09 | 2020-11-13 | 车智互联（北京）科技有限公司 | Article title generation method and device and computing equipment |
| CN113609263A (en) * | 2021-09-30 | 2021-11-05 | 网娱互动科技(北京)股份有限公司 | Method and system for automatically generating articles |
| KR102410260B1 (en) * | 2022-03-07 | 2022-06-22 | 와이에스에이 주식회사 | Method, device and system for automatic creation and confirmation of advertisement content based on artificial intelligence |
Non-Patent Citations (2)
| Title |
|---|
| 基于LDA模型的HSK作文生成;徐艳华 等;数据分析与知识发现;第02期(第09期);80-87 * |
| 新闻专题的高效组织和生成新方法;谭浩 等;科技导报(第07期);48-51 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116611417A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9501467B2 (en) | Systems, methods, software and interfaces for entity extraction and resolution and tagging | |
| CA2807494C (en) | Method and system for integrating web-based systems with local document processing applications | |
| US11687826B2 (en) | Artificial intelligence (AI) based innovation data processing system | |
| CN110442728A (en) | Sentiment dictionary construction method based on word2vec automobile product field | |
| CN112115252B (en) | Intelligent auxiliary writing processing method and device, electronic equipment and storage medium | |
| CN110929007A (en) | Electric power marketing knowledge system platform and application method | |
| US20200110802A1 (en) | Systems and Methods of Machine Learning for Digital Assets and Message Creation | |
| WO2011117594A1 (en) | System | |
| CN115526171A (en) | Intention identification method, device, equipment and computer readable storage medium | |
| CN116611417B (en) | Automatic article generating method, system, computer equipment and storage medium | |
| CN115496830A (en) | Method and device for generating product demand flow chart | |
| CN109948128B (en) | Auxiliary editing system | |
| CN112559753A (en) | Management framework of natural language text processing and analyzing task based on business process management technology | |
| CN117453895B (en) | Intelligent customer service response method, device, equipment and readable storage medium | |
| US11995414B1 (en) | Automatic post-editing systems and methods | |
| Atri et al. | A Pragmatic Approach to Web-Summarizer System | |
| CN117540004B (en) | Industrial domain intelligent question-answering method and system based on knowledge graph and user behavior | |
| US20230385541A1 (en) | Method and system for producing unified natural language processing objects | |
| CN110738040B (en) | Comment expansion method and comment expansion system | |
| CN118171650A (en) | Completely unsupervised large language model fine tuning training platform | |
| Azevedo et al. | BPMN Model and Text Instructions Automatic Synchronization. | |
| CN114064878A (en) | Natural language data marking method and system based on reinforcement learning | |
| KR20240054797A (en) | System and method for increasing sentence data for crime analysis | |
| Mészáros | Agent-supported knowledge acquisition for digital humanities research | |
| Trubitsyna | Usage Artificial Intelligence Toolkit for Improving Translations to English |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |